Some of it is due to bigger data, but the majority is definitely ML. For constant data, the error rate dropped dramatically due to much improved algorithms.
15 years ago, voice recognition was all hidden markov model based. The data sets were limited, in part due to the cost of collection, but mostly because larger datasets didn't significantly improve accuracy.
As algorithms improved, larger datasets became more important as more data did actually improve accuracy.
15 years ago, voice recognition was all hidden markov model based. The data sets were limited, in part due to the cost of collection, but mostly because larger datasets didn't significantly improve accuracy.
As algorithms improved, larger datasets became more important as more data did actually improve accuracy.